Founding Engineer, AI Hyderabad · onsite · Full Time Apply →

CENNA Systems Inc.; Hyderabad; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Cenna Systems Inc. is seeking an AI Engineer to design, implement, and optimize multi-agent AI systems that automate enterprise workflows. You will work on agent frameworks, LLM orchestration, and production-grade AI components that go beyond chatbots to actionable automation.

The role focuses on building reliable agentic platforms, integrating with enterprise systems, and advancing RAG and embedding-based solutions in a fast-paced environment.

Qualifications

• 3-5 years of software engineering experience with at least 1-2 years in AI/ML or LLM applications.
• Strong programming skills in Python.
• Hands-on experience with agent frameworks: LangChain, LangGraph, CrewAI, AutoGen, Haystack or similar.
• Experience building applications with LLM APIs (OpenAI, Anthropic, Azure OpenAI, open-source models).
• Understanding of prompt engineering, chain-of-thought reasoning, and tool-use patterns.
• Familiarity with RAG architectures, vector databases, and embedding models.
• Ability to debug complex AI systems and iterate based on real-world failures.
• Strong communication skills and ability to work cross-functionally.

Responsibilities

• Design and build multi-agent systems that orchestrate complex business process automation
• Work with agent frameworks to build reliable, production-grade agentic workflows
• Implement and optimize LLM-powered reasoning, planning, and tool-use capabilities
• Build RAG pipelines and knowledge retrieval systems to ground agents in enterprise context
• Fine-tune and evaluate Small Language Models for domain-specific tasks
• Develop prompt engineering strategies and evaluation frameworks for agent reliability
• Collaborate with integration engineers to connect agents with enterprise systems
• Debug and improve agent behavior based on production feedback and failure analysis

Skills

Python programming

AI/LLM development

Agent frameworks

LLM APIs (OpenAI, Anthropic, Azure)

Prompt engineering

RAG architectures

Vector databases

Debugging AI systems

Cross-functional collaboration

Tools

LangChain

LangGraph

CrewAI

AutoGen

Haystack

OpenAI API

Anthropic API

Azure OpenAI

Job description

Build our agentic services platform from zero to one. Own backend architecture from initial concept through production deployment to enterprise scale.

About this role

We're looking for an AI Engineer to build and improve the intelligent core of our agentic platform. You'll work on multi-agent systems, LLM orchestration, and the AI capabilities that power our enterprise automation. This is a hands-on role where you'll design, implement, and optimize AI systems that execute real business processes — not just chatbots, but agents that get work done.

Responsibilities

• Design and build multi-agent systems that orchestrate complex business process automation
• Work with agent frameworks (LangChain, LangGraph, CrewAI, AutoGen, or similar) to build reliable, production-grade agentic workflows
• Implement and optimize LLM-powered reasoning, planning, and tool-use capabilities
• Build RAG pipelines and knowledge retrieval systems to ground agents in enterprise context
• Fine-tune and evaluate Small Language Models (SLMs) for domain-specific tasks
• Develop prompt engineering strategies and evaluation frameworks for agent reliability
• Collaborate with integration engineers to connect agents with enterprise systems
• Debug and improve agent behavior based on production feedback and failure analysis

Requirements

• 3-5 years of experience in software engineering, with at least 1-2 years focused on AI/ML or LLM applications
• Strong programming skills in Python
• Hands-on experience with agent frameworks: LangChain, LangGraph, CrewAI, AutoGen, Haystack, or similar
• Experience building applications with LLM APIs (OpenAI, Anthropic, Azure OpenAI, open-source models)
• Understanding of prompt engineering, chain-of-thought reasoning, and tool-use patterns
• Familiarity with RAG architectures, vector databases, and embedding models
• Ability to debug complex AI systems and iterate based on real-world failures
• Strong communication skills and ability to work cross-functionally

Nice to Have

• Experience fine-tuning LLMs or training custom models (LoRA, PEFT, etc.)
• Familiarity with browser/computer-use agents and UI automation
• Experience with ML infrastructure: model serving, GPU optimization, inference at scale
• Background in reinforcement learning or decision-making systems
• Understanding of enterprise IT, ITSM, or business process automation
• Startup experience or comfort working in fast-paced, ambiguous environments